Research on stock index prediction based on ARIMA-CNN-LSTM model

DOI

10.2991/978-94-6463-408-2_63How to use a DOI?

Keywords

stock index forecasting; ARIMA model; CNN-LSTM combination model; deep learning; financial markets

Abstract

As financial markets become ever more complicated and unpredictable, traditional stock index prediction models no longer meet the high frequency and big data market environment. To enhance forecast accuracy this study proposes a hybrid model comprised of autoregressive integral sliding average model (ARIMA), convolutional neural network (CNN), and long short term memory network (LSTM). According to the pre-data processing; Then the time-critical time series features are extracted. Finally, the sequence of capturing data dependence and output prediction results is carried out. ARIMA, CNN and LSTM models will be used. After experimental verification of multiple stock index data, compared with other traditional prediction models, ARIMA-CNN-LSTM model is better in prediction accuracy and robustness. The model provides a powerful tool for financial workers to better understand market dynamics and make informed investment decisions.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Ziyan Zhang
PY  - 2024
DA  - 2024/05/07
TI  - Research on stock index prediction based on ARIMA-CNN-LSTM model
BT  - Proceedings of the 9th International Conference on Financial Innovation and Economic Development (ICFIED 2024)
PB  - Atlantis Press
SP  - 558
EP  - 565
SN  - 2352-5428
UR  - https://doi.org/10.2991/978-94-6463-408-2_63
DO  - 10.2991/978-94-6463-408-2_63
ID  - Zhang2024
ER  -